The unmanned aerial vehicle (UAV), as a remote sensing platform, has attracted many researchers in precision agriculture because of its operational flexibility and capability of producing high spatial and temporal resolution images of agricultural fields. This study proposed machine learning (ML) models and their ensembles for peanut yield prediction using UAV multispectral data. We utilized five bands (red, green, blue, near-infra-red (NIR) and red-edge) multispectral images acquired at various growth stages of peanuts using UAV. The correlation between spectral bands and yield was analyzed for each growth stage, which showed that the maturity stages had a significant correlation between peanut yield and spectral bands: red, green, NIR and red edge (REDE). Using these four bands spectral data, we assessed the potential for peanut yield prediction using multiple linear regression and seven non-linear ML models whose hyperparameters were optimized using simulated annealing (SA). The best three ML models, random forest (RF), support vector machine (SVM) and XGBoost, were then selected to construct a cooperative yield prediction framework with both the best ML model and the ensemble scheme from the best three as comparable recommendations to the farmers.

Because of the recent development in advanced sensors, data acquisition platforms, and data analysis methods, unmanned aerial vehicle (UAV) or drone-based remote sensing has gained significant attention from precision agriculture (PA) researchers. The massive amount of raw data collected from such sensing platforms demands large-scale data processing algorithms such as machine learning and deep learning methods. Therefore, it is timely to provide a detailed survey that assimilates, categorises, and compares the performance of various machine learning and deep learning methods for PA. This paper summarises and synthesises the recent works using a general pipeline of UAV-based remote sensing for precision agriculture research. We classify the different features extracted from UAV imagery for various agriculture applications, showing the importance of each feature for the performance of the crop model and demonstrating how the multiple feature fusion can improve the models' performance. In addition, we compare and contrast the performances of various machine learning and deep learning models for three important crop trait estimations: yield estimation, disease detection and crop classification. Furthermore, the recent trends in applications of UAVs for PA are briefly discussed in terms of their importance, and opportunities. Finally, we recite the potential challenges and suggest future avenues of research in this field.